A Dialogue Training Method and System Based on Artificial Intelligence

Abstract

This application relates to the technical field of data processing, and discloses a dialogue training method and system based on artificial intelligence, including: analyzing pre-obtained employee sales data through a preset employee ability evaluation model to obtain an employee sales level; analyzing the employee sales data through a preset customer intention recognition model to construct a customer type map; combining the employee sales level and the customer type map, and generating multiple dialogue scenarios through a preset dialogue generation model; by analyzing the change in the sales ability of employees during each dialogue practice process, using a preset dialogue optimization model to adjust the difficulty of the next dialogue scenario to achieve dynamic dialogue training; this application generates dialogue scenarios based on the employee sales level and the customer type map, making the dialogue practice more targeted, dynamically adjusting the difficulty of the dialogue scenario, making the training more targeted and effective, and helping employees quickly master dialogue skills.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a dialogue training method and system based on artificial intelligence. Background Art

[0002] In the traditional training process of salesperson's conversation skills, manual training is adopted, which takes a lot of time, and the unified training settings ignore the differences in sales capabilities of different salespersons, and cannot provide targeted training for each employee; the existing technology cannot perform personalized generation in combination with the ability levels of employees and different types of customers, and lacks a mechanism to dynamically adjust the difficulty of the conversation scenario according to the changes in employees' capabilities during the conversation practice process, and cannot effectively help employees gradually improve their sales capabilities.

[0003] Based on the above problems existing in the prior art, in order to solve at least one of the above problems, the present application proposes a dialogue training method and system based on artificial intelligence. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the main object of the present invention is to provide a dialogue training method and system based on artificial intelligence, which can effectively solve the problems in the background art. The specific technical solutions of the present invention are as follows:

[0005] A dialogue training method based on artificial intelligence includes:

[0006] Analyze the pre-obtained employee sales data through a preset employee ability evaluation model to obtain the employee sales level;

[0007] Analyze the employee sales data through a preset customer intention recognition model to construct a customer type map;

[0008] Combine the employee sales level and the customer type map, and generate multiple dialogue scenarios through a preset dialogue generation model, wherein the multiple dialogue scenarios are generated corresponding to different customer types;

[0009] After the end of a conversation practice process, analyze the employee sales intention and customer intention in the previous conversation process through a preset intention analysis model to construct an employee sales intention network and a customer intention network;

[0010] Through a preset hierarchical matching model, perform hierarchical matching on the employee sales intention network and the customer intention network to obtain a matching degree value, wherein the hierarchical matching includes coarse-grained matching, fine-grained matching and dynamic weight allocation;

[0011] According to the relationship between the matching degree value and a preset matching degree threshold, adjust the difficulty of the next dialogue scenario through a preset dialogue optimization model to achieve dynamic dialogue training.

[0012] Specifically, analyzing the pre-acquired employee sales data through a preset employee ability evaluation model to obtain the employee sales level, including:

[0013] Extracting features from the sales dialogue text in the pre-acquired employee sales data through a preset text feature extraction model to generate a text feature vector;

[0014] Analyzing the behavior logs in the employee sales data to obtain a time-series behavior feature vector;

[0015] Analyzing the transaction records in the employee sales data to obtain a transaction success rate;

[0016] Combining the text feature vector, the time-series behavior feature vector, and the transaction success rate, and evaluating the sales ability of the employee through a preset employee ability evaluation model to obtain an employee ability matrix;

[0017] Determining the employee sales level according to the employee ability matrix.

[0018] Specifically, analyzing the employee sales data through a preset customer intention recognition model to construct a customer type map, including:

[0019] Extracting the corresponding customer dialogue records from the employee sales data;

[0020] According to the customer dialogue records, analyzing the customer type and the intention of the customer in each conversation through a preset customer intention recognition model to construct a customer type map, where the customer type in the customer type map is the root node, the intention is the child node, and the conversion probability between different intentions is the weight of the edge.

[0021] Specifically, according to the customer dialogue records, analyzing the customer type and the intention of the customer in each conversation through a preset customer intention recognition model to construct a customer type map, including:

[0022] Analyzing the intention of the customer in each conversation according to the customer dialogue records through a preset customer intention recognition model to obtain an intention recognition result;

[0023] Identifying the corresponding customer type according to the customer dialogue records through a preset customer type recognition model;

[0024] Calculating the conversion probability of the corresponding customer type between different intentions through the intention recognition result of the customer in each conversation;

[0025] Construct a customer type graph with the customer type as the root node, different intents as child nodes, and the conversion probability between corresponding intents as the edge weight.

[0026] Specifically, by combining the employee sales level and the customer type graph, generate multiple dialogue scenarios through a preset dialogue generation model, where the multiple dialogue scenarios are generated corresponding to different customer types, including:

[0027] Match in the customer type graph according to the employee sales level through a preset mapping rule to obtain the corresponding customer type sub-graph;

[0028] Generate multiple dialogue scenarios through a preset dialogue generation model based on the customer type sub-graph combined with the employee's real-time dialogue content.

[0029] Specifically, the generating multiple dialogue scenarios through a preset dialogue generation model based on the customer type sub-graph combined with the employee's real-time dialogue content includes:

[0030] Initialize and select an initial intent from the customer type sub-graph as the starting point of the dialogue;

[0031] Generate the first simulated reply of the customer through a preset dialogue generation model based on the employee sales level combined with the starting point of the dialogue;

[0032] Analyze the transfer probability of the customer's intent in combination with the employee's reply result to the first simulated reply;

[0033] Select the intent with the highest transfer probability as the next customer intent and generate the next simulated reply of the customer through a preset dialogue generation model;

[0034] Repeat the reply generation process until the dialogue ends.

[0035] Specifically, the hierarchical matching of the employee sales intent network and the customer intent network through a preset hierarchical matching model to obtain the matching degree value includes:

[0036] Analyze the coarse-grained matching degree between the employee sales intent network and the customer intent network to obtain the coarse-grained matching degree value;

[0037] Analyze the fine-grained matching degree between the employee sales intent network and the customer intent network to obtain the fine-grained matching degree value;

[0038] Allocate weights to the coarse-grained matching degree value and the fine-grained matching degree value through a preset hierarchical matching model according to the preset business objective to obtain the corresponding weights;

[0039] Calculate the matching degree value by performing weighted calculation on the coarse-grained matching degree value and the fine-grained matching degree value with corresponding weights.

[0040] Specifically, analyzing the coarse-grained matching degree between the employee sales intention network and the customer intention network to obtain the coarse-grained matching degree value includes:

[0041] Count the occurrence times of various intentions in the employee sales intention network and the customer intention network respectively;

[0042] Calculate the first matching ratio based on the corresponding relationship between various intentions in the employee sales intention network and the customer intention network and the occurrence times;

[0043] Assign corresponding weights to various intentions through a preset first dynamic weight assignment model;

[0044] Perform weighted calculation by combining the first matching ratio and the corresponding weights to obtain the coarse-grained matching degree value.

[0045] Specifically, analyzing the fine-grained matching degree between the employee sales intention network and the customer intention network to obtain the fine-grained matching degree value includes:

[0046] Divide each intention in the employee sales intention network and the customer intention network through a preset intention division model to obtain intention sub-categories;

[0047] Calculate the second matching ratio according to the occurrence times of each intention sub-category in the employee sales intention network and the customer intention network and the corresponding relationship between intention sub-categories;

[0048] Assign corresponding weights to each intention sub-category through a preset second dynamic weight assignment model;

[0049] Perform weighted calculation by combining the second matching ratio and the corresponding weights to obtain the fine-grained matching degree value.

[0050] An artificial intelligence-based dialogue training system for implementing the artificial intelligence-based dialogue training method described above, includes:

[0051] An employee sales level analysis module, which analyzes pre-acquired employee sales data through a preset employee ability evaluation model to obtain the employee sales level;

[0052] A customer type graph construction module, which analyzes the employee sales data through a preset customer intention recognition model to construct a customer type graph;

[0053] The dialogue generation module combines the employee sales level and the customer type map, and generates multiple dialogue scenarios through a preset dialogue generation model, where the multiple dialogue scenarios are generated corresponding to different customer types;

[0054] The network construction module, after the end of a dialogue practice process, analyzes the employee sales intention and the customer intention in the previous dialogue process through a preset intention analysis model, and constructs an employee sales intention network and a customer intention network;

[0055] The network matching module performs hierarchical matching on the employee sales intention network and the customer intention network through a preset hierarchical matching model to obtain a matching degree value, where the hierarchical matching includes coarse-grained matching, fine-grained matching, and dynamic weight assignment;

[0056] The dialogue optimization module adjusts the difficulty of the next dialogue scenario through a preset dialogue optimization model according to the relationship between the matching degree value and a preset matching degree threshold to achieve dynamic dialogue training.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] This application constructs a customer type map based on multi-source sales data, generates dialogue scenarios according to the employee sales level and the customer type map, making the dialogue practice more targeted. Employees with different ability levels can be matched with dialogue scenarios suitable for their own levels, and at the same time, simulation exercises are carried out for different types of customers to improve the employees' ability to handle various customers. At the same time, by analyzing the matching degree of the employee sales intention and the customer intention in the dialogue practice process, the difficulty of the next dialogue scenario is dynamically adjusted to ensure that the employees can gradually improve their sales ability, enhance the training effect, make the training more targeted and effective, and thus help the employees master the dialogue skills faster. Description of the Drawings

[0059] Figure 1 It is a work flow chart of an artificial intelligence-based dialogue training method in Embodiment 1 of the present invention;

[0060] Figure 2 It is a schematic diagram of the construction of the customer type map in Embodiment 1 of the present invention;

[0061] Figure 3 It is a schematic diagram of the hierarchical matching process of the employee sales intention network and the customer intention network in Embodiment 1 of the present invention;

[0062] Figure 4 It is a schematic diagram of the structure of an artificial intelligence-based dialogue training system in Embodiment 2 of the present invention. Detailed Embodiments

[0063] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification.

[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may be practiced in other ways different from those described herein. Persons skilled in the art may make similar extensions without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0065] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or alternative embodiments that exclude each other from other embodiments.

[0066] Embodiment 1

[0067] This embodiment provides an artificial intelligence-based dialogue training method. As Figure 1 shown, the artificial intelligence-based dialogue training method includes:

[0068] S101. Analyze the pre-acquired employee sales data through a preset employee ability evaluation model to obtain the employee sales level;

[0069] S102. Analyze the employee sales data through a preset customer intention recognition model to construct a customer type map;

[0070] S103. Combine the employee sales level and the customer type map, and generate multiple dialogue scenarios through a preset dialogue generation model, where the multiple dialogue scenarios are generated corresponding to different customer types;

[0071] S104. After the end of a dialogue practice process, analyze the employee sales intention and customer intention in the previous dialogue process through a preset intention analysis model to construct an employee sales intention network and a customer intention network;

[0072] S105. Through a preset hierarchical matching model, perform hierarchical matching on the employee sales intention network and the customer intention network to obtain a matching degree value, where the hierarchical matching includes coarse-grained matching, fine-grained matching, and dynamic weight allocation;

[0073] S106. According to the relationship between the matching degree value and a preset matching degree threshold, adjust the difficulty of the next dialogue scenario through a preset dialogue optimization model to achieve dynamic dialogue training.

[0074] In this embodiment, corresponding dialogue scenarios are generated according to the sales ability levels of employees and different customer types to assist employees in conducting sales conversations and helping them improve their sales conversation skills. At the same time, during the training process, according to the improvement of employees' sales abilities, the dialogue difficulty of each sales scenario is dynamically adjusted to adapt to the individual abilities of employees and improve the training effect. Compared with the traditional fixed-mode training scenarios, the dialogue training scenarios intelligently generated by this solution can adapt to the differences of different employees and provide personalized training scenarios for each employee, thus quickly improving the dialogue skills of employees.

[0075] In this embodiment, first, employee sales data is collected, including multi-source data such as sales conversation texts, behavior logs, and transaction records. The sales conversation texts record the content of the communication between employees and customers; the behavior logs record the behavior information such as the time and frequency of the interaction between employees and customers; the transaction records reflect the actual results of sales, such as the volume of transactions and the amount of transactions. The sales ability of employees can be analyzed and evaluated based on the employee sales data. The employee sales data is analyzed through a preset employee ability evaluation model to obtain the employee sales level. According to the employee sales level, personalized generation is performed for the dialogue scenarios of each employee, so that the generated dialogue scenarios are more in line with the actual sales level of employees and avoid the limitations of single-dimensional evaluation.

[0076] Specifically, by analyzing different types corresponding to different customers, diverse dialogue scenarios are provided. According to the message reply situation of customers in the employee sales data, the customer types are analyzed, and a customer type map is constructed. The customer intentions and types in the employee sales data are identified through a preset customer intention recognition model. According to the customer types and the changes in customer intentions during each conversation, the conversion probability between different intentions of the corresponding customer types is calculated. Using the customer type as the root node, different intentions as the child nodes, and the conversion probability between the corresponding intentions as the edge weights, a customer type map is constructed. By constructing the customer type map, the intention distribution of different customer types and the conversion relationship between intentions can be intuitively displayed, providing rich customer information for generating targeted dialogue scenarios, helping employees better understand customers, and improving the effect of sales communication.

[0077] Furthermore, according to the obtained employee sales level, it is mapped to the customer types suitable for the employees. Combining the characteristics and intention conversion relationships of different customer types in the customer type map, a preset dialogue generation model is used to generate targeted dialogue scenarios, providing personalized dialogue scenarios for each employee. The generated dialogue takes into account both the ability level of the employees and the actual types and behavior patterns of the customers, and can effectively improve the quality and effect of employees' dialogue practice and enhance the employees' ability to handle different customers.

[0078] Meanwhile, after each dialogue practice session, based on the complete record of the dialogue practice process, through a pre-set intention analysis model, specifically a natural language processing model based on deep learning, the organized dialogue data is input into the model round by round. The model conducts intention recognition on the statements of the employee and the customer in each round. For example, the model determines that the intention of an employee's statement in a certain round is "emphasis on product advantages", and the intention of the customer's response is "raising price objections". According to the recognized employee intentions and customer intentions, an employee sales intention network and a customer intention network are respectively constructed. For the employee sales intention network, the recognized employee intentions are used as nodes. During the dialogue process, when the employee transitions from the "product introduction" intention to the "solving customer doubts" intention, a directed edge is created between these two nodes to represent the intention change; the customer intention network is constructed in the same way. By constructing the employee sales intention network and the customer intention network, the matching degree between the employee's response situation and the customer's intention can be quickly analyzed, and then the change in the employee's sales ability can be analyzed.

[0079] Specifically, through hierarchical matching, the matching degree between the employee sales intention network and the customer intention network is analyzed. Hierarchical matching includes three steps: coarse-grained matching, fine-grained matching, and dynamic weight assignment. Coarse-grained matching can consider the overall matching situation between the employee and customer intention categories from a macroscopic level. Fine-grained matching conducts matching analysis on sub-categories or specific content details within the intention. Dynamic weight assignment adjusts the importance of the coarse-grained and fine-grained matching results in the calculation of the final matching degree according to the business objective and the actual dialogue situation. Through this hierarchical matching method, the one-sidedness of single-dimensional matching is avoided, and the fit degree between the employee sales intention and the customer intention can be comprehensively and accurately evaluated, obtaining a comprehensive matching degree value, providing a quantitative basis for adjusting the difficulty of the dialogue scenario, and helping to achieve more reasonable dynamic dialogue training.

[0080] Furthermore, according to the relationship between the calculated matching degree value and the pre-set matching degree threshold, the pre-set matching degree threshold is set according to the employee ability improvement goal and the actual business situation. When the matching degree value is higher than the matching degree threshold, it indicates that the employee performed well in the previous dialogue practice and can handle the current difficulty, and the difficulty of the next dialogue scenario can be appropriately increased to continuously challenge the employee's ability. When the matching degree is lower than the matching degree threshold, it means that the employee has deficiencies at the current difficulty level, and the difficulty of the next dialogue scenario needs to be reduced so that the employee can gradually improve their ability. Through the pre-set dialogue optimization model, relevant parameters for generating the dialogue scenario are adjusted according to the comparison result to achieve dynamic difficulty adjustment. Through the dynamic adaptive adjustment of the dialogue practice difficulty, the practice difficulty is flexibly adjusted according to the actual ability performance of the employee, avoiding the employee being frustrated due to excessive difficulty or being unable to effectively improve their ability due to too low difficulty. Continuously providing an effective practice environment for the employee, promoting the steady improvement of the employee's sales ability, enhancing the pertinence and effectiveness of the dialogue training, and ultimately improving the overall level of the enterprise sales team.

[0081] This application constructs a customer type map based on multi-source sales data, generates a dialogue scenario according to the employee sales level and the customer type map, making the dialogue practice more targeted. Employees with different ability levels can be matched to dialogue scenarios suitable for their own levels. At the same time, simulation exercises are carried out for different types of customers to improve the employees' ability to handle various customers. Also, by analyzing the matching degree of the sales intention and the customer intention of the employees during the dialogue practice, the difficulty of the next dialogue scenario is dynamically adjusted to ensure that the employees can gradually improve their sales ability, enhance the training effect, make the training more targeted and effective, and thus help the employees master the dialogue skills faster.

[0082] Further, analyzing the pre-acquired employee sales data through a preset employee ability evaluation model to obtain the employee sales level, including:

[0083] S201. According to the sales dialogue text in the pre-acquired employee sales data, extract features from the sales dialogue text through a preset text feature extraction model to generate a text feature vector;

[0084] S202. Analyze the behavior log in the employee sales data to obtain a time-series behavior feature vector;

[0085] S203. Analyze the transaction records in the employee sales data to obtain the transaction success rate;

[0086] S204. Combine the text feature vector, the time-series behavior feature vector and the transaction success rate, and evaluate the sales ability of the employee through a preset employee ability evaluation model to obtain an employee ability matrix;

[0087] S205. Determine the employee sales level according to the employee ability matrix.

[0088] This embodiment conducts real-time evaluation of the employees' sales ability. By analyzing the employees' sales data from multiple dimensions and evaluating the employees' sales ability considering multiple factors, an accurate employee ability evaluation result is obtained. First, through a preset text feature extraction model, features are extracted from the sales dialogue text in the employee sales data, and the key information in the text is converted into vector form, reflecting the characteristics of the employees in aspects such as language use in the dialogue, product introduction methods, and conversation skills in interacting with customers, providing data support for evaluating the employees' sales ability from the text dimension.

[0089] Exemplarily, the sales dialogue text is cleaned to remove noise data therein, such as irrelevant special characters, garbled codes, etc. At the same time, the text is tokenized, splitting continuous sentences into individual words for easy feature extraction. For example, for the sentence "The performance of our product is very excellent", after tokenization, words such as "we", "this", "product", "of", "performance", "very", "excellent" are obtained. The text feature extraction model is specifically a neural network model based on word vectors, which is trained on a large amount of text data. The model predicts a word based on the context, and in this process, each word is mapped to a low-dimensional vector space, such that words with similar semantics are closer in the vector space. For example, during the training process, the two words "product" and "commodity" with similar semantics will have relatively close positions of their corresponding word vectors in the space. In this way, each word in the sales dialogue text is converted into a corresponding word vector, and then these word vectors are weighted and aggregated to obtain the text feature vector of the entire sales dialogue text. By converting the unstructured sales dialogue text into structured vector data, key ability points such as the language style and professional knowledge expression of employees in communication can be captured, providing an important basis for comprehensively evaluating employees' sales capabilities.

[0090] Specifically, analyze the behavior logs in the employee sales data. The behavior logs record various behaviors of employees' interactions with customers, such as the first contact time, subsequent follow-up time, communication methods (phone, email, face-to-face, etc.) and communication frequency, etc. First, sort out these log data to ensure the accuracy and integrity of the data, and sort the data in chronological order. According to the sorted behavior log data, extract time interval features, communication frequency features and behavior pattern features. The time interval features are obtained by calculating the time interval from the first contact between the employee and the customer to the first follow-up and the time interval between each follow-up. The communication frequency feature is obtained by counting the number of communications between the employee and the customer within a certain time period. The behavior pattern feature is obtained by analyzing the changing rules of the communication methods adopted by the employee at different time points. Combining these features to obtain a time-series behavior feature vector, which can reflect the employee's customer management ability, sales rhythm grasping ability, etc., and complement each other with indicators such as text feature vectors and transaction success rates, making the evaluation of employees' sales capabilities more comprehensive.

[0091] Meanwhile, analyze the transaction records in the employee sales data, calculate the transaction success rate. From the transaction records in the employee sales data, filter out the records of successful transactions and total transactions. The successful transaction records can be determined according to the signs of transaction completion (such as receipt of payment, signing of contract, etc.). Count the number of successful transactions and the number of total transactions, calculate the transaction success rate. Through the transaction success rate, the ability of employees to convert sales opportunities into actual results can be reflected. Incorporate the transaction success rate into the employee ability evaluation system to make the evaluation results more in line with the actual situation.

[0092] Furthermore, comprehensively analyze the extracted text feature vectors, time-series behavior feature vectors, and transaction success rate. Through a preset employee ability evaluation model, specifically a pre-trained neural network model, comprehensively process these multi-dimensional data. The model learns the relationship between each feature and the employee's sales ability based on a large amount of historical data, so as to comprehensively evaluate the employee's sales ability and output an employee ability matrix. Through the fusion and comprehensive analysis of multi-source data, the sales ability of employees can be evaluated comprehensively and accurately. According to the calculated employee ability matrix, determine the employee's sales level through certain mapping rules. By converting the complex employee ability matrix into a simple and intuitive employee sales level, employees can be classified and managed and receive targeted training. Employees with different sales levels can be matched with different difficulty levels and types of dialogue practice scenarios to improve the efficiency of training and management.

[0093] Exemplarily, according to the actual needs of the enterprise and the characteristics of the sales business, formulate the mapping rules between the employee ability matrix and the employee sales level. Weight and sum the scores of each dimension in the employee ability matrix according to the assigned weights to obtain a comprehensive score. Then, divide different grade intervals according to this comprehensive score. For example, a comprehensive score between 80-100 is the senior sales level, 60-79 is the intermediate sales level, and below 60 is the junior sales level.

[0094] Furthermore, analyze the employee sales data through a preset customer intention recognition model to construct a customer type map, including:

[0095] S301. Extract the corresponding customer conversation records from the employee sales data;

[0096] S302. According to the customer conversation records, analyze the customer type and the intention of the customer in each conversation through a preset customer intention recognition model, and construct a customer type map. Among them, the customer type in the customer type map is the root node, the intention is the sub-node, and the conversion probability between different intentions is the weight of the edge.

[0097] Further, based on the customer conversation records, analyze the customer type and the customer's intention in each conversation through a preset customer intention recognition model, and construct a customer type map, including:

[0098] S401. Based on the customer conversation records, analyze the intention of the customer in each conversation through a preset customer intention recognition model to obtain an intention recognition result;

[0099] S402. Based on the customer conversation records, identify the corresponding customer type through a preset customer type recognition model;

[0100] S403. Calculate the conversion probability between different intentions of the corresponding customer type through the intention recognition result of the customer in each conversation;

[0101] S404. Use the customer type as the root node, different intentions as the child nodes, and the conversion probability between the corresponding intentions as the edge weights to construct a customer type map.

[0102] In this embodiment, extract customer conversation records from employee sales data, analyze customer intentions and behaviors. Based on the customer conversation records, identify customer intentions through a preset customer intention recognition model. The customer intention recognition model is specifically a convolutional neural network model. Perform preprocessing such as data cleaning, noise removal, and word segmentation on the extracted customer conversation records, and input the preprocessed customer conversation records into a pre-trained model. The model calculates and outputs the probability distribution of the intention category corresponding to each conversation, and selects the intention category with the highest probability as the recognition result. For example, if the model outputs that the probability of a certain conversation belonging to the "product consultation" intention is 0.7, the probability of belonging to the "purchase intention inquiry" intention is 0.2, and the probability of belonging to other intentions is 0.1, then the intention recognition result of this conversation is determined to be "product consultation"; by analyzing customer intentions, we can deeply understand customer needs and then determine the customer type.

[0103] Specifically, based on the customer conversation records, identify the customer type through a preset customer type recognition model. Different customers show different behavior patterns and language styles in the conversation. The preset customer type recognition model classifies customers by learning these features. The model is specifically a random forest model. Based on historical customer data, train and mine the common features of different types of customers to obtain a pre-trained customer type recognition model. Extract various features from the customer conversation records for customer type recognition, such as the conversation length, the number of professional words used, the type of questions (open-ended questions, closed-ended questions), etc.; input the extracted customer type features into the customer type recognition model, and the model outputs the corresponding customer type. By classifying customers, it helps to provide diverse conversation scenarios.

[0104] Furthermore, during the communication between customers and employees, the customers' intentions may change. By counting the number of conversions between various intentions for different customer types and combining with the total number of conversations, the intention conversion probability is calculated to reflect the behavioral patterns and demand change trends of customers at different stages. Analyze each record in the customer conversation records to determine the customer type, starting intention, and target intention, and calculate the corresponding intention conversion probability. For example, in a conversation record of the "potential customer" type, the starting intention is "product consultation", and after communication, the target intention becomes "inquiry about purchase intention". For each customer type and for each pair of starting intention and target intention, divide the number of conversions by the total number of occurrences of the starting intention to obtain the conversion probability between these two intentions for the corresponding customer type. For example, in the "potential customer" type, the number of conversions from "product consultation" to "inquiry about purchase intention" is 20 times, and the total number of occurrences of the "product consultation" intention is 100 times, so the conversion probability is 20÷100 = 0.2.

[0105] Specifically, as Figure 2 shown, take the analyzed customer types as the root nodes, take various intentions as the child nodes and connect them to the corresponding customer type root nodes, and take the conversion probability between intentions as the weight of the connecting edge to form a directed weighted graph, construct a customer type map, which visually displays customer behavior and intention information through the customer type map, and corresponding dialogue scenarios can be quickly generated according to the customer type map.

[0106] Furthermore, by combining the employee sales level and the customer type map, multiple dialogue scenarios are generated through a preset dialogue generation model, where the multiple dialogue scenarios are generated corresponding to different customer types, including:

[0107] S501. According to the employee sales level, match in the customer type map through a preset mapping rule to obtain the corresponding customer type sub-graph;

[0108] S502. According to the customer type sub-graph and combining with the employee's real-time conversation content, generate multiple dialogue scenarios through a preset dialogue generation model.

[0109] In this embodiment, according to the sales level of each employee, the corresponding customer types suitable for each employee are matched in the constructed customer type graph. Employees with different ability levels are suitable for dealing with different types of customers. Based on the customers they are good at dealing with, customers they are not good at dealing with are matched for them to improve the ability of each employee to adapt to different types of customers. According to the preset mapping rules, the relevant intention relationships of the customer types and their associated ones that match the employees' abilities are screened out in the customer type graph to form a customer type sub-graph, providing customer simulation scenarios with appropriate difficulty and type for employees at different ability levels, preventing employees from being unable to effectively improve their abilities due to facing overly simple or complex customer simulation scenarios, improving the pertinence and effectiveness of dialogue practice, and promoting the gradual improvement of employees' sales abilities.

[0110] Specifically, according to the customer types and their intention relationship information in the matched customer type sub-graph, combined with the real-time dialogue content of the employees, the preset dialogue generation model is used to simulate the responses of customers under different intentions, and the conversation is gradually advanced according to the dialogue logic to generate multiple complete dialogue scenarios close to the actual sales scenarios, enabling employees to be fully exercised in the simulation environment; the generated dialogue scenarios are both based on the real behavior patterns of customers and can be dynamically adjusted according to the real-time performance of employees, highly simulating the real sales scenarios, enabling employees to better master dialogue skills in practice, improving the ability to handle different customers and various dialogue situations, and enhancing the practicality and effect of sales training.

[0111] Further, generating multiple dialogue scenarios according to the customer type sub-graph in combination with the real-time dialogue content of the employees through the preset dialogue generation model includes:

[0112] S601. Initialize and select an initial intention from the customer type sub-graph as the starting point of the conversation;

[0113] S602. According to the employee's sales level and in combination with the starting point of the conversation, generate the first simulated response of the customer through the preset dialogue generation model;

[0114] S603. Analyze the transfer probability of the customer's intention in combination with the response result of the employee to the first simulated response;

[0115] S604. Select the intention with the highest transfer probability as the next customer intention, and generate the next simulated response of the customer through the preset dialogue generation model;

[0116] S605. Repeat the response generation process until the conversation ends.

[0117] In this embodiment, an initial intent is selected and initialized in the customer type sub-graph to obtain the starting point of the conversation. The occurrence frequencies of each intent node in the customer type sub-graph are counted. For example, a graph algorithm is used to traverse the customer type sub-graph, and the number of times each intent node is connected is recorded. In a specific customer type sub-graph, it is found through statistics that the "product consultation" intent node has the most connections, indicating that in the interaction between such customers and employees, it is relatively common to start the conversation with product consultation. Therefore, the "product consultation" intent is preferentially selected as the initial conversation starting point. By reasonably selecting the initial intent, it is possible to simulate the common opening methods of customers in real sales scenarios, enabling employees to quickly enter the simulated conversation scenario, and the diverse selection strategies help improve employees' abilities to handle different customer openings.

[0118] Specifically, according to the employee's sales level combined with the selected conversation starting point, through a preset conversation generation model, the first simulated response result is generated. The employee's sales level corresponds to different ability levels. When employees at different levels communicate with customers, the response methods and content expectations of customers are different. For employees with a lower level, the customer response results are relatively gentle; for employees with a higher level, the customer response results can be more incisive, increasing the difficulty of dialogue practice for higher-level employees. The conversation generation model is trained based on a large amount of historical sales conversation data and learns the language patterns under different employee sales levels and customer intents. By inputting the employee's sales level and the conversation starting point into the model, the model can generate a customer's first simulated response that conforms to the scenario based on this information. The generated simulated response takes into account the actual ability level of the employee, making the dialogue practice more targeted. When employees face customer responses that match their own abilities, they can better adapt to and improve their communication skills. At the same time, the conversation generation model generates simulated responses based on historical data, ensuring the authenticity and reasonableness of the responses and enhancing the credibility of the simulated scenario.

[0119] Exemplarily, for employees at the junior sales level, the conversation starting point is the "product consultation" intent. After concatenating the vector representing the junior sales level and the "product consultation" intent vector and inputting them into the trained conversation generation model, the model, through internal calculations, outputs the customer's first simulated response as "I am more concerned about the price range of your products. Can you introduce them first?"

[0120] Specifically, after the employee responds to the scenario, the employee's response to the customer's simulated response will affect the direction of the customer's intention. By analyzing the employee's response content and combining the existing intention conversion probability information in the customer type sub-graph, the next intention of the customer and its probability distribution are inferred. The intention with the highest transfer probability is selected as the next intention of the customer. According to the next intention, the next customer simulated response result is generated through a preset dialogue generation model. By dynamically analyzing the customer's intention transfer based on the employee's real-time response, the dialogue scenario becomes more interactive and realistic. The employee can feel the impact of their response on the customer's intention in the simulation, thus learning how to guide the customer's intention and enhancing the initiative and effectiveness of sales communication.

[0121] At the same time, continuously repeat the process of generating customer responses, analyzing intention transfers, and generating customer responses again to simulate the multi-round interaction in a real sales conversation. Set the dialogue end condition. When the end condition is met, it is considered that a complete dialogue scenario construction is completed. By constructing different dialogue scenarios multiple times, the employee's sales dialogue ability is comprehensively exercised; through multi-round dialogues to simulate real sales scenarios, the employee's dialogue ability in the entire sales process is comprehensively exercised, including links such as opening, communication promotion, handling objections, and closing deals; the diverse dialogue scenario generation methods can enable the employee to come into contact with the reactions and dialogue directions of more different types of customers, enhancing the employee's comprehensive ability to handle complex sales scenarios.

[0122] Furthermore, the hierarchical matching of the employee sales intention network and the customer intention network is performed through a preset hierarchical matching model to obtain a matching degree value, including:

[0123] S701. Analyze the coarse-grained matching degree between the employee sales intention network and the customer intention network to obtain a coarse-grained matching degree value;

[0124] S702. Analyze the fine-grained matching degree between the employee sales intention network and the customer intention network to obtain a fine-grained matching degree value;

[0125] S703. According to the preset business objectives, assign weights to the coarse-grained matching degree value and the fine-grained matching degree value through a preset hierarchical matching model to obtain corresponding weights;

[0126] S704. Perform weighted calculation on the coarse-grained matching degree value and the fine-grained matching degree value with the corresponding weights to obtain a matching degree value.

[0127] Such as Figure 3, in this embodiment, the matching degree between the employee sales intention network and the customer intention network is calculated. Through hierarchical matching, the coarse-grained matching degree value and the fine-grained matching degree value are calculated respectively, and the weight values of the coarse-grained matching degree value and the fine-grained matching degree value are dynamically allocated. First, analyze the coarse-grained matching degree between the employee sales intention network and the customer intention network. Coarse-grained matching examines the matching situation between the employee sales intention network and the customer intention network from a macroscopic perspective, paying attention to the overall category of intentions. By counting the occurrence times of various intentions in the two networks and calculating the matching ratio based on their corresponding relationships, and then combining the preset weights, the coarse-grained matching degree value is finally obtained; by calculating the coarse-grained matching value, the matching situation between the employee and the customer intention can be quickly evaluated from the overall level, providing a macroscopic matching degree index.

[0128] Furthermore, analyze the fine-grained matching degree between the employee sales intention network and the customer intention network. Fine-grained matching delves into the interior of the intention, further divides each intention into sub-categories, calculates a more detailed matching ratio through counting the occurrence times of sub-categories and the corresponding relationships between sub-categories, and then combines their respective weights to obtain the fine-grained matching degree value; through fine-grained matching, the matching situation between the employee and the customer in terms of intention details can be deeply explored, and the employee's ability performance in dealing with the specific demand details of customers can be discovered, making the matching degree analysis more comprehensive and accurate.

[0129] At the same time, according to the business objectives, weight allocation is carried out for the calculated coarse-grained matching degree value and fine-grained matching degree value. Different business objectives have different emphases on coarse-grained matching and fine-grained matching in the sales process; for example, when the business focus is on quickly facilitating transactions, the matching degree of transaction-related intentions in coarse-grained matching is more critical; while when the business emphasizes the in-depth exploration and satisfaction of customer needs, the importance of the fine-grained matching degree is higher; the preset hierarchical matching model flexibly allocates weights for the coarse-grained matching degree value and the fine-grained matching degree value according to these business objectives. Through weight allocation, the matching degree calculation can closely fit the current business needs of the enterprise, highlighting the key requirements for different aspects of the employee's sales ability in different business stages, and helping the enterprise more effectively evaluate the employee's performance and optimize the sales strategy according to the actual business situation.

[0130] Exemplarily, when the business objective focuses on quickly facilitating transactions, the weight of the coarse-grained matching degree value can be set to 0.7, and the weight of the fine-grained matching degree value can be set to 0.3; when the business objective is to improve customer satisfaction and deeply explore customer needs, the weight of the coarse-grained matching degree value can be set to 0.4, and the weight of the fine-grained matching degree value can be set to 0.6.

[0131] Specifically, the calculated coarse-grained matching value and fine-grained matching value are weighted according to the assigned weights, and the intention matching at the macro and micro levels is comprehensively considered to obtain a matching value that fully reflects the degree of fit between the employee's sales intention and the customer's intention; avoiding the limitations of single-dimensional matching analysis. It can more accurately reflect the overall fit between the employee and the customer's intention in the sales conversation, and provide a more scientific and comprehensive basis for the difficulty adjustment of the conversation scene and the evaluation of employee capabilities.

[0132] Furthermore, the coarse-grained matching degree of the employee sales intention network and the customer intention network is analyzed to obtain a coarse-grained matching degree value, including:

[0133] S801, counting the number of occurrences of each type of intention in the employee sales intention network and the customer intention network respectively;

[0134] S802, calculating a first matching ratio according to the correspondence between the various intentions in the employee sales intention network and the customer intention network and the number of occurrences;

[0135] S803, assigning corresponding weights to various types of intentions through a preset first dynamic weight assignment model;

[0136] S804: Perform weighted calculation based on the first matching ratio and the corresponding weight to obtain a coarse-grained matching degree value.

[0137] In this embodiment, first, the number of occurrences of each type of intent in the employee sales intention network and the customer intention network is counted respectively, and the employee sales intention network and the customer intention network are traversed by a depth-first search (DFS) algorithm. During the traversal process, each time an intent node is accessed, it is checked whether the intent category already exists in the counting record. If not, a new record item is created and the count is initialized to 1; if it already exists, the corresponding count is increased by 1; based on the correspondence between the intents in the employee sales intention network and the customer intention network and the counted number of occurrences, the intent matching ratio is calculated to obtain a first matching ratio; by comparing the matching ratios of different corresponding intent groups, it can be found out which intent matches the employees perform better in and which ones need improvement, thereby providing direction for targeted training and strategy adjustments.

[0138] Specifically, the corresponding weights are assigned to various types of intentions through a preset first dynamic weight allocation model. Different intentions have different importance levels in the sales process. The first dynamic weight allocation model dynamically assigns weights to various types of intentions according to the degree of influence of the intention on the sales result. When calculating the coarse-grained matching degree value, the matching situation of important intentions can be highlighted to affect the overall matching degree; the calculated matching ratios of various corresponding intentions are weighted and calculated with their corresponding weights, and the matching situations of all corresponding intention groups are integrated to obtain a coarse-grained matching degree value that can comprehensively reflect the matching degree between the employee's sales intention and the customer's intention at the macro level; through the coarse-grained matching degree value, the matching situations of different intention groups and their importance can be comprehensively considered, and compared with the simple calculation of the matching ratio, it can more accurately evaluate the employee's ability to grasp the customer's main intention in the overall sales conversation.

[0139] Exemplarily, through the graph traversal algorithm, the employee sales intention network and the customer intention network are traversed respectively, and the occurrence times of each intention category are recorded during the traversal process; based on the logic and experience of the sales business, the corresponding relationship between intention categories is determined. For example, "product introduction" corresponds to "product consultation", "promotion and promotion" corresponds to "preference attention", etc.; then, for each group of corresponding intentions, its matching ratio is calculated; the calculation formula is: matching ratio = min(employee intention occurrence times, customer intention occurrence times) / max(employee intention occurrence times, customer intention occurrence times). For example, for "product introduction" (appearing 15 times on the employee side) and "product consultation" (appearing 12 times on the customer side), the matching ratio = 12 / 15 = 0.8; using the preset first dynamic weight allocation model, weights are assigned to various types of intentions according to the importance of different intentions to the sales result; for example, the "closing a deal" intention is crucial to the sales result, and the weight can be set to 0.7; the "product introduction" intention weight is set to 0.3. For each group of corresponding intentions, its matching ratio is multiplied by the corresponding weight, and then all the products are accumulated to obtain the coarse-grained matching degree value.

[0140] Further, analyzing the fine-grained matching degree between the employee sales intention network and the customer intention network to obtain the fine-grained matching degree value includes:

[0141] S901. Through a preset intention division model, each intention in the employee sales intention network and the customer intention network is divided to obtain intention sub-categories;

[0142] S902. According to the occurrence times of each intention sub-category in the employee sales intention network and the customer intention network, combined with the corresponding relationship between intention sub-categories, calculate the second matching ratio;

[0143] S903. Assign corresponding weights to each intention sub-category through a preset second dynamic weight allocation model;

[0144] S904. Perform weighted calculation by combining the second matching ratio and the corresponding weight to obtain the fine-grained matching degree value.

[0145] In this embodiment, the fine-grained matching degree between the employee sales intention network and the customer intention network is analyzed, and the fine-grained matching degree value is calculated. First, the intentions in the employee sales intention network and the customer intention network are divided through a preset intention division model to obtain intention subcategories. The preset intention division model is obtained based on in-depth understanding of the sales business and a large amount of historical data analysis. By subdividing the intentions in the network, considering the complexity and diversity of the intentions in the sales conversation and the problem that a single intention classification cannot fully display its details, the specific intention details expressed by the employee and the customer in the conversation can be analyzed more accurately through intention subdivision.

[0146] Exemplarily, the intention division model is specifically a clustering model based on machine learning. First, a large amount of text data containing intention descriptions is clustered and trained to learn the feature differences between different intention subcategories, and then new intentions are divided. For example, a large amount of text data about product introduction is clustered into several different clusters, and each cluster corresponds to an intention subcategory. For example, function-related text is clustered into the "function introduction" cluster, and performance-related text is clustered into the "performance introduction" cluster; the information of each intention node in the employee sales intention network and the customer intention network is input into the intention division model, and the model outputs the corresponding intention subcategory; for example, the "product introduction" intention node in the employee sales intention network is divided into multiple intention subcategory nodes such as "function introduction" and "performance introduction" after being processed by the model.

[0147] Specifically, similar to the coarse-grained matching, the fine-grained matching calculates the matching ratio by comparing the occurrence times of the employee and customer intention subcategories and combining the corresponding relationship between the intention subcategories to obtain the second matching ratio; according to the different importance of different intention subcategories in the sales process, a corresponding weight is assigned to each intention subcategory through a preset second dynamic weight allocation model. The second dynamic weight allocation model is specifically a decision tree model. The decision tree model is trained through a large amount of historical data to obtain a pre-trained second dynamic weight allocation model. The various intention subcategories are input into the model, and the model outputs the weight value corresponding to each intention subcategory. The calculated second matching ratios of various corresponding intention subcategories are weighted with their corresponding weights to obtain a fine-grained matching degree value that can comprehensively reflect the matching degree between the employee sales intention and the customer intention at the micro level; by calculating the fine-grained matching degree, compared with the simple matching ratio calculation, it can more accurately evaluate the employee's ability to grasp the specific needs details of the customer in the overall sales conversation.

[0148] Exemplarily, through the intention division model, each intention in the employee sales intention network and the customer intention network is subdivided. The "product introduction" intention is subdivided into sub-categories such as "function introduction", "performance introduction", "material introduction", etc.; the "product consultation" intention is subdivided into sub-categories such as "function inquiry", "performance inquiry", "material inquiry", etc.; the occurrence times of each intention sub-category are respectively counted, and then, for each corresponding group of intention sub-categories, the matching ratio is calculated. For example, the "function introduction" sub-category of the employee appears 10 times, and the "function inquiry" sub-category of the customer appears 8 times, and the matching ratio = 8 / 10 = 0.8; through the second dynamic weight assignment model, according to the influence degree of the sub-category on the sales process, weights are assigned to each intention sub-category. For some products, the "performance introduction" and "performance inquiry" sub-categories have a greater impact on the sales decision, and the weight is set to 0.4; the weight of the "material introduction" and "material inquiry" sub-categories is set to 0.2, etc.; multiply the matching ratio of each sub-category by the corresponding weight, and accumulate all the products to obtain the fine-grained matching degree value.

[0149] Embodiment 2

[0150] In this embodiment, as Figure 4 , a dialogue training system based on artificial intelligence is provided for implementing the described dialogue training method based on artificial intelligence, including:

[0151] An employee sales level analysis module analyzes pre-obtained employee sales data through a preset employee ability evaluation model to obtain the employee sales level;

[0152] A customer type map construction module analyzes the employee sales data through a preset customer intention recognition model to construct a customer type map;

[0153] A dialogue generation module combines the employee sales level and the customer type map, and generates multiple dialogue scenarios through a preset dialogue generation model, where the multiple dialogue scenarios are generated corresponding to different customer types;

[0154] A network construction module analyzes the employee sales intention and the customer intention in the previous dialogue process through a preset intention analysis model after the end of a dialogue practice process, and constructs an employee sales intention network and a customer intention network;

[0155] A network matching module performs hierarchical matching on the employee sales intention network and the customer intention network through a preset hierarchical matching model to obtain a matching degree value, where the hierarchical matching includes coarse-grained matching, fine-grained matching and dynamic weight assignment;

[0156] The dialogue optimization module adjusts the difficulty of the next dialogue scenario through a preset dialogue optimization model according to the relationship between the matching degree value and the preset matching degree threshold, so as to achieve dynamic dialogue training.

[0157] In this embodiment, the employee sales level analysis module includes a data collection unit, a text feature extraction unit, a behavior log analysis unit, a transaction record analysis unit, and an employee ability evaluation unit. This module comprehensively evaluates the sales ability of employees, quantifies it into the employee sales level, enables the system to provide appropriate dialogue practice scenarios according to the actual level of employees, and promotes the improvement of employees' sales ability; the customer type map construction module includes a dialogue record extraction unit, a customer intention recognition unit, an intention conversion probability calculation unit, and a map construction unit. This module deeply analyzes the intentions and behavior patterns of customers in sales dialogues, constructs a customer type map, provides rich customer information for the dialogue generation module, thus generating more practical and targeted dialogue scenarios. At the same time, it also helps enterprises better understand customers and formulate accurate sales strategies.

[0158] Specifically, the dialogue generation module includes a customer type sub-graph matching unit, a dialogue starting point selection unit, a simulated reply generation unit, an intention transfer analysis unit, and a dialogue scenario construction unit. This module combines the employee sales level and the customer type map to generate multiple dialogue scenarios corresponding to different customer types, simulates real sales scenarios through the dialogue scenarios, provides diversified dialogue practice materials for employees, and helps employees improve their communication ability with different types of customers; the network construction module includes a data collection unit, an intention analysis model, and a network construction unit. This module constructs an employee sales intention network and a customer intention network by analyzing each dialogue record after each dialogue practice, providing a basis for analyzing the matching degree between the two; the network matching module includes a coarse-grained matching unit, a fine-grained matching unit, a dynamic weight assignment unit, and a matching degree calculation unit. This module analyzes the matching degree between the employee sales intention network and the customer intention network through a preset hierarchical matching model, comprehensively considers coarse-grained matching, fine-grained matching, and dynamic weight assignment, and obtains an accurate matching degree value, providing a basis for adjusting the difficulty of the dialogue scenario; the dialogue optimization module includes a threshold comparison unit, a difficulty adjustment decision unit, and a dialogue optimization unit. This module adjusts the difficulty of the next dialogue scenario according to the relationship between the matching degree value and the preset matching degree threshold, realizes dynamic dialogue training, and helps employees gradually improve their sales ability.

[0159] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification only illustrates the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A dialogue training method based on artificial intelligence, characterized in that, Including: Analyze the pre-acquired employee sales data through a preset employee ability evaluation model to obtain the employee sales level; Analyze the employee sales data through a preset customer intention recognition model to construct a customer type map; Combine the employee sales level and the customer type map, and generate multiple dialogue scenarios through a preset dialogue generation model, where the multiple dialogue scenarios are generated corresponding to different customer types; After the end of a dialogue practice process, analyze the employee sales intention and customer intention in the previous dialogue process through a preset intention analysis model to construct an employee sales intention network and a customer intention network, where the employee intention in the employee sales intention network is used as a node, and a directed edge is established between the nodes to point to the transformation intention, and the customer intention in the customer intention network is used as a node, and a directed edge is established between the nodes to point to the transformation intention; Through a preset hierarchical matching model, perform hierarchical matching on the employee sales intention network and the customer intention network to obtain a matching degree value, where the hierarchical matching includes coarse-grained matching, fine-grained matching and dynamic weight allocation; According to the relationship between the matching degree value and a preset matching degree threshold, adjust the difficulty of the next dialogue scenario through a preset dialogue optimization model to achieve dynamic dialogue training; The step of performing hierarchical matching on the employee sales intention network and the customer intention network through a preset hierarchical matching model to obtain a matching degree value includes: Analyze the coarse-grained matching degree between the employee sales intention network and the customer intention network to obtain a coarse-grained matching degree value; Analyze the fine-grained matching degree between the employee sales intention network and the customer intention network to obtain a fine-grained matching degree value; According to the preset business goal, allocate weights to the coarse-grained matching degree value and the fine-grained matching degree value through a preset hierarchical matching model to obtain corresponding weights; Perform weighted calculation on the coarse-grained matching degree value and the fine-grained matching degree value with the corresponding weights to obtain a matching degree value; The step of analyzing the coarse-grained matching degree between the employee sales intention network and the customer intention network to obtain a coarse-grained matching degree value includes: Respectively count the occurrence times of various intentions in the employee sales intention network and the customer intention network; Calculate a first matching ratio according to the corresponding relationship between various intentions in the employee sales intention network and the customer intention network and the occurrence times; Analyze the importance of various intentions through a preset first dynamic weight allocation model and allocate corresponding weights to various intentions; Perform weighted calculation by combining the first matching ratio and the corresponding weights to obtain a coarse-grained matching degree value; The step of analyzing the fine-grained matching degree between the employee sales intention network and the customer intention network to obtain a fine-grained matching degree value includes: Through a preset intention division model, divide each intention in the employee sales intention network and the customer intention network to obtain intention sub-categories; Calculate a second matching ratio according to the occurrence times of each intention sub-category in the employee sales intention network and the customer intention network and the corresponding relationship between the intention sub-categories; Allocate corresponding weights to each intention sub-category through a preset second dynamic weight allocation model; Perform weighted calculation by combining the second matching ratio and the corresponding weight to obtain a fine-grained matching degree value.

2. The method for dialogue training based on artificial intelligence according to claim 1, wherein, Analyze the pre-obtained employee sales data through a preset employee ability evaluation model to obtain the employee sales level, including: Extract features from the sales conversation text in the pre-obtained employee sales data through a preset text feature extraction model to generate a text feature vector. Analyze the behavior log in the employee sales data to obtain a time-series behavior feature vector. Analyze the transaction records in the employee sales data to obtain the transaction success rate. Combine the text feature vector, time-series behavior feature vector, and transaction success rate, and evaluate the sales ability of the employee through a preset employee ability evaluation model to obtain an employee ability matrix. Determine the employee sales level according to the employee ability matrix.

3. The method for dialogue training based on artificial intelligence according to claim 1, characterized in that Analyze the employee sales data through a preset customer intention recognition model to construct a customer type map, including: Extract the corresponding customer conversation records from the employee sales data. According to the customer conversation records, analyze the customer type and the customer's intention in each conversation through a preset customer intention recognition model to construct a customer type map, where the customer type in the customer type map is the root node, the intention is the child node, and the conversion probability between different intentions is the weight of the edge.

4. The method for dialogue training based on artificial intelligence according to claim 3, wherein According to the customer conversation records, analyze the customer type and the customer's intention in each conversation through a preset customer intention recognition model to construct a customer type map, including: Analyze the customer's intention in each conversation through a preset customer intention recognition model according to the customer conversation records to obtain an intention recognition result. Identify the corresponding customer type according to the customer conversation records through a preset customer type recognition model. Calculate the conversion probability of the corresponding customer type between different intentions through the intention recognition result of the customer in each conversation. Construct a customer type map with the customer type as the root node, different intentions as the child nodes, and the conversion probability between the corresponding intentions as the weight of the edge.

5. A dialogue training method based on artificial intelligence according to claim 1, characterized in that Combine the employee sales level and the customer type map, and generate multiple conversation scenarios through a preset conversation generation model, where the multiple conversation scenarios are generated corresponding to different customer types, including: Match in the customer type map according to the employee sales level through a preset mapping rule to obtain a corresponding customer type sub-map. Generate multiple conversation scenarios through a preset conversation generation model according to the customer type sub-map combined with the employee's real-time conversation content.

6. The method for dialogue training based on artificial intelligence according to claim 5, characterized in that, Generate multiple conversation scenarios through a preset conversation generation model according to the customer type sub-map combined with the employee's real-time conversation content, including: Initialize and select an initial intention from the customer type sub-map as the starting point of the conversation. Generate the first simulated reply of the customer through a preset conversation generation model according to the employee sales level combined with the starting point of the conversation. Analyze the transfer probability of the customer's intention in combination with the employee's reply result to the first simulated reply. Select the intent with the highest transfer probability as the next customer intent, and generate the next simulated response of the customer through a preset dialogue generation model; Repeat the response generation process until the dialogue ends.

7. An artificial intelligence-based dialogue training system, characterized in that, A method for artificial intelligence-based dialogue training as claimed in any one of claims 1 to 6, comprising: An employee sales level analysis module that analyzes pre-acquired employee sales data through a preset employee ability evaluation model to obtain the employee sales level; A customer type graph construction module that analyzes the employee sales data through a preset customer intent recognition model to construct a customer type graph; A dialogue generation module that combines the employee sales level and the customer type graph and generates multiple dialogue scenarios through a preset dialogue generation model, wherein the multiple dialogue scenarios are generated corresponding to different customer types; A network construction module that analyzes the employee sales intent and the customer intent during the previous dialogue process through a preset intent analysis model after the end of a dialogue practice process to construct an employee sales intent network and a customer intent network; A network matching module that hierarchically matches the employee sales intent network and the customer intent network through a preset hierarchical matching model to obtain a matching degree value, wherein the hierarchical matching includes coarse-grained matching, fine-grained matching, and dynamic weight assignment; A dialogue optimization module that adjusts the difficulty of the next dialogue scenario through a preset dialogue optimization model according to the relationship between the matching degree value and a preset matching degree threshold to achieve dynamic dialogue training.

Images